Using conditional probabilistic queries for NCA and variants in PLS-SEM

The article below shows how one can use conditional probabilistic queries for NCA and variants in PLS-SEM. It focuses on necessary and sufficient conditions analyses (Jan Dul’s original NCA and variants) employing latent variables.

Kock, N. (2025). Using conditional probabilistic queries for NCA and variants in PLS-SEM. Data Analysis Perspectives Journal, 6(3), 1-6.

Link to full-text file for this and other DAPJ articles:

https://scriptwarp.com/dapj/#Published_Articles

Abstract:

We discuss the use of conditional probabilistic queries for necessary and sufficient conditions analyses (Jan Dul’s original NCA and variants) employing latent variables within the partial least squares structural equation modeling (PLS-SEM) context. While traditional PLS-SEM path coefficients establish linear causal links, they do not directly estimate the conditional probabilities central to NCA. These probabilities are crucial for both researchers and practitioners seeking a deeper understanding of necessary and sufficient conditions. This article demonstrates how to conduct bivariate and multivariate conditions analyses to systematically assess such relationships. Using an illustrative model analyzed with WarpPLS, we show how to identify specific levels of latent variables (e.g., job satisfaction and organizational commitment) that are necessary or sufficient to achieve a target outcome (e.g., above-average job performance). This methodology offers a powerful complement to classic SEM, allowing for the identification of essential prerequisites for desired outcomes.

Video demonstrating the techniques employed in the article:

Best regards to all!